RNNet-MST: A ResNet-50 with Multi-Scale Transformer Blocks for Pulmonary Nodule Classification and Attention-Based Localization on Chest X-Ray Images.
Authors
Affiliations (7)
Affiliations (7)
- College of Information Systems and Technology, Pamantasan ng Lungsod ng Maynila, Manila 1002, Philippines.
- Institut de Science des Matériaux de Mulhouse (IS2M), CNRS, UHA, UMR 7361, 68057 Mulhouse, France.
- University Research Center, Pamantasan ng Lungsod ng Maynila, Manila 1002, Philippines.
- School of Chemical, Biological, Materials Engineering and Sciences, Mapúa University, Manila 1002, Philippines.
- School of Health Sciences and Nursing, Mapúa University, Makati 1205, Philippines.
- College of Medicine, Pamantasan ng Lungsod ng Maynila, Manila 1002, Philippines.
- Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701401, Taiwan.
Abstract
<b>Background/Objectives</b>: Lung cancer survival depends on early detection; however, in the Philippines, high radiologist workloads and the anatomical complexity of chest X-rays (CXRs) contribute to missed pulmonary nodules and false-negative diagnoses. This study aims to develop an enhanced deep learning model to improve nodule classification and localization sensitivity. <b>Methods</b>: We propose RNNet-MST, an extension of ResNet-50 that incorporates Multi-Scale Transformer blocks for global context modeling and a custom spatial attention mechanism for attention-based weak localization of disease-relevant regions. The model was trained and evaluated on the NODE21 chest X-ray dataset and compared with a baseline ResNet-50 using classification metrics, with attention maps used for weak localization analysis. <b>Results</b>: RNNet-MST demonstrated consistent improvements over the baseline ResNet-50 across evaluated metrics. Mean Nodule Recall improved from 88.02 ± 1.92% to 91.55 ± 1.41%, reducing false negatives. Mean Test Precision reached 90.46 ± 0.99%, and mean Nodule F1-Score improved to 90.99 ± 0.39%. On the isolated small-nodule subset, RNNet-MST achieved a 12.3% improvement in sensitivity over the baseline. <b>Conclusions</b>: The integration of multi-scale transformer features improved classification sensitivity, while the attention mechanism provided weak localization cues that aligned more closely with annotated nodule regions than the baseline. RNNet-MST shows potential as a diagnostic support tool, warranting further validation on larger and more diverse clinical datasets to reduce perceptual errors and facilitate early lung cancer detection in resource-constrained settings.